[PATCH 1/3] accounting: task counters for disk/network

From: Gerlof Langeveld
Date: Wed Apr 02 2008 - 03:49:34 EST


From: Gerlof Langeveld <gerlof@xxxxxxxxxxxxxx>

Proper performance analysis requires the availability of system level
and process level counters for CPU, memory, disk and network utilization.
The current kernel offers the system level counters, however process level
counters are only (sufficiently) available for CPU and memory utilization.

The kernel feature "task I/O accounting" currently maintains
per process counters for the number of bytes transferred to/from disk.
These counters are available via /proc/pid/io. It is still not possible
to find out which process issues the physical disk transfer. Besides,
not *all* disk transfers are accounted to processes (e.g. swap-transfers
by kswapd, journaling transfers).

This patch extends "task I/O accounting" by counting real *physical*
disk transfers per process and by counting IPv4/IPv6 socket transfers
per process.
The modified output generated for /proc/pid/io will be as follows:

$ cat /proc/3179/io
rchar: 49934
wchar: 4
syscr: 27
syscw: 1
read_bytes: 200704
write_bytes: 4096
cancelled_write_bytes: 0
disk_read: 8 <---- this line is added
disk_read_sect: 392 <---- this line is added
disk_write: 0 <---- this line is added
disk_write_sect: 0 <---- this line is added
tcp_send: 0 <---- this line is added
tcp_send_bytes: 0 <---- this line is added
tcp_recv: 0 <---- this line is added
tcp_recv_bytes: 0 <---- this line is added
udp_send: 27 <---- this line is added
udp_send_bytes: 1296 <---- this line is added
udp_recv: 27 <---- this line is added
udp_recv_bytes: 29484 <---- this line is added
raw_send: 0 <---- this line is added
raw_recv: 0 <---- this line is added

The performance monitor 'atop' uses a similar kernel patch for
several years already to be able to show these per process statistics.

Modified source files
include/linux/task_io_accounting.h: addition of new counters to the
struct task_io_accounting

fs/proc/base.c: generate output via /proc/pid/io

block/ll_rw_blk.c: per process counting of physical
disk access

net/socket.c: per process counting of socket
transfers

kernel/acct.c: add number of disk reads/writes to
standard accounting record

Since "task I/O accounting" is currently optional (CONFIG_TASK_IO_ACCOUNTING),
all modifications are ifdef'd with the same macro as well.
Patch applies to kernel version 2.6.24.4

Signed-off-by: Gerlof Langeveld <gerlof@xxxxxxxxxxxxxx>
---

diff -uprN -X linux-2.6.24.4-vanilla/Documentation/dontdiff linux-2.6.24.4-vanilla/block/ll_rw_blk.c linux-2.6.24.4-modified/block/ll_rw_blk.c
--- linux-2.6.24.4-vanilla/block/ll_rw_blk.c 2008-03-24 19:49:18.000000000 +0100
+++ linux-2.6.24.4-modified/block/ll_rw_blk.c 2008-03-25 13:52:14.000000000 +0100
@@ -2739,6 +2739,19 @@ static void drive_stat_acct(struct reque
disk_round_stats(rq->rq_disk);
rq->rq_disk->in_flight++;
}
+
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ switch (rw) {
+ case READ:
+ current->group_leader->ioac.dsk_rio += new_io;
+ current->group_leader->ioac.dsk_rsz += rq->nr_sectors;
+ break;
+ case WRITE:
+ current->group_leader->ioac.dsk_wio += new_io;
+ current->group_leader->ioac.dsk_wsz += rq->nr_sectors;
+ break;
+ }
+#endif
}

/*
diff -uprN -X linux-2.6.24.4-vanilla/Documentation/dontdiff linux-2.6.24.4-vanilla/fs/proc/base.c linux-2.6.24.4-modified/fs/proc/base.c
--- linux-2.6.24.4-vanilla/fs/proc/base.c 2008-03-24 19:49:18.000000000 +0100
+++ linux-2.6.24.4-modified/fs/proc/base.c 2008-03-25 13:52:14.000000000 +0100
@@ -2174,7 +2174,21 @@ static int proc_pid_io_accounting(struct
#endif
"read_bytes: %llu\n"
"write_bytes: %llu\n"
- "cancelled_write_bytes: %llu\n",
+ "cancelled_write_bytes: %llu\n"
+ "disk_read: %llu\n"
+ "disk_read_sect: %llu\n"
+ "disk_write: %llu\n"
+ "disk_write_sect: %llu\n"
+ "tcp_send: %llu\n"
+ "tcp_send_bytes: %llu\n"
+ "tcp_recv: %llu\n"
+ "tcp_recv_bytes: %llu\n"
+ "udp_send: %llu\n"
+ "udp_send_bytes: %llu\n"
+ "udp_recv: %llu\n"
+ "udp_recv_bytes: %llu\n"
+ "raw_send: %llu\n"
+ "raw_recv: %llu\n",
#ifdef CONFIG_TASK_XACCT
(unsigned long long)task->rchar,
(unsigned long long)task->wchar,
@@ -2183,7 +2197,21 @@ static int proc_pid_io_accounting(struct
#endif
(unsigned long long)task->ioac.read_bytes,
(unsigned long long)task->ioac.write_bytes,
- (unsigned long long)task->ioac.cancelled_write_bytes);
+ (unsigned long long)task->ioac.cancelled_write_bytes,
+ (unsigned long long)task->ioac.dsk_rio,
+ (unsigned long long)task->ioac.dsk_rsz,
+ (unsigned long long)task->ioac.dsk_wio,
+ (unsigned long long)task->ioac.dsk_wsz,
+ (unsigned long long)task->ioac.tcp_snd,
+ (unsigned long long)task->ioac.tcp_ssz,
+ (unsigned long long)task->ioac.tcp_rcv,
+ (unsigned long long)task->ioac.tcp_rsz,
+ (unsigned long long)task->ioac.udp_snd,
+ (unsigned long long)task->ioac.udp_ssz,
+ (unsigned long long)task->ioac.udp_rcv,
+ (unsigned long long)task->ioac.udp_rsz,
+ (unsigned long long)task->ioac.raw_snd,
+ (unsigned long long)task->ioac.raw_rcv);
}
#endif

diff -uprN -X linux-2.6.24.4-vanilla/Documentation/dontdiff linux-2.6.24.4-vanilla/include/linux/task_io_accounting.h linux-2.6.24.4-modified/include/linux/task_io_accounting.h
--- linux-2.6.24.4-vanilla/include/linux/task_io_accounting.h 2008-03-24 19:49:18.000000000 +0100
+++ linux-2.6.24.4-modified/include/linux/task_io_accounting.h 2008-03-25 13:52:14.000000000 +0100
@@ -30,6 +30,23 @@ struct task_io_accounting {
* information loss in doing that.
*/
u64 cancelled_write_bytes;
+
+ /*
+ * Number of physical reads and writes to disk by this task
+ * and the accumulated size of these physical transfers.
+ */
+ u64 dsk_rio, dsk_wio;
+ u64 dsk_rsz, dsk_wsz;
+
+ /*
+ * Number of sends and receives issued for IPv4/IPv6 by
+ * this task on TCP, UDP and raw sockets with their accumulated size.
+ */
+ u64 tcp_snd, tcp_rcv;
+ u64 tcp_ssz, tcp_rsz;
+ u64 udp_snd, udp_rcv;
+ u64 udp_ssz, udp_rsz;
+ u64 raw_snd, raw_rcv;
};
#else
struct task_io_accounting {
diff -uprN -X linux-2.6.24.4-vanilla/Documentation/dontdiff linux-2.6.24.4-vanilla/kernel/acct.c linux-2.6.24.4-modified/kernel/acct.c
--- linux-2.6.24.4-vanilla/kernel/acct.c 2008-03-24 19:49:18.000000000 +0100
+++ linux-2.6.24.4-modified/kernel/acct.c 2008-03-25 13:55:07.000000000 +0100
@@ -497,7 +497,11 @@ static void do_acct_process(struct file
ac.ac_exitcode = pacct->ac_exitcode;
spin_unlock_irq(&current->sighand->siglock);
ac.ac_io = encode_comp_t(0 /* current->io_usage */); /* %% */
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ ac.ac_rw = encode_comp_t(current->ioac.dsk_rio + current->ioac.dsk_wio);
+#else
ac.ac_rw = encode_comp_t(ac.ac_io / 1024);
+#endif
ac.ac_swaps = encode_comp_t(0);

/*
diff -uprN -X linux-2.6.24.4-vanilla/Documentation/dontdiff linux-2.6.24.4-vanilla/net/socket.c linux-2.6.24.4-modified/net/socket.c
--- linux-2.6.24.4-vanilla/net/socket.c 2008-03-24 19:49:18.000000000 +0100
+++ linux-2.6.24.4-modified/net/socket.c 2008-03-25 13:52:14.000000000 +0100
@@ -551,10 +551,30 @@ static inline int __sock_sendmsg(struct
si->size = size;

err = security_socket_sendmsg(sock, msg, size);
- if (err)
- return err;
+ if (!err)
+ err = sock->ops->sendmsg(iocb, sock, msg, size);

- return sock->ops->sendmsg(iocb, sock, msg, size);
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ if (err >= 0 && sock->sk) {
+ switch (sock->sk->sk_family) {
+ case PF_INET:
+ case PF_INET6:
+ switch (sock->sk->sk_type) {
+ case SOCK_STREAM:
+ current->group_leader->ioac.tcp_snd++;
+ current->group_leader->ioac.tcp_ssz += size;
+ break;
+ case SOCK_DGRAM:
+ current->group_leader->ioac.udp_snd++;
+ current->group_leader->ioac.udp_ssz += size;
+ break;
+ case SOCK_RAW:
+ current->group_leader->ioac.raw_snd++;
+ }
+ }
+ }
+#endif
+ return err;
}

int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
@@ -633,10 +653,31 @@ static inline int __sock_recvmsg(struct
si->flags = flags;

err = security_socket_recvmsg(sock, msg, size, flags);
- if (err)
- return err;
+ if (!err)
+ err = sock->ops->recvmsg(iocb, sock, msg, size, flags);

- return sock->ops->recvmsg(iocb, sock, msg, size, flags);
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ if (err >= 0 && sock->sk) {
+ switch (sock->sk->sk_family) {
+ case PF_INET:
+ case PF_INET6:
+ switch (sock->sk->sk_type) {
+ case SOCK_STREAM:
+ current->group_leader->ioac.tcp_rcv++;
+ current->group_leader->ioac.tcp_rsz += size;
+ break;
+ case SOCK_DGRAM:
+ current->group_leader->ioac.udp_rcv++;
+ current->group_leader->ioac.udp_rsz += size;
+ break;
+ case SOCK_RAW:
+ current->group_leader->ioac.raw_rcv++;
+ break;
+ }
+ }
+ }
+#endif
+ return err;
}

int sock_recvmsg(struct socket *sock, struct msghdr *msg,
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/